Human Attuned Machine Learning Tool for Dune Annotation in ArcGIS Pro

Abstract

The Human-Attuned Machine Learning (HAML) Dune Annotation Tool (DAT) is a custom ArcGIS Pro plugin that facilitates quick, simple, and accurate annotation of coastal dune formations based on digital elevation models collected from LiDAR or other remote sensing methodologies. It implements an intuitive user interface consisting of basic lines and vertices which are first generated by a machine-learning backend and then adjusted or corrected by the user, if necessary, in an iterative process following the methods of previous HAML work. The intended purpose of the tool is to enable geospatial analysts to efficiently and accurately annotate coastal dune formations, so the tool is designed to follow the standard procedures for detecting dune crests and dune toes that have previously been used to conduct studies on the coastal response to storm surges and other adverse coastal phenomena. It utilizes several fail-safes and quality control checks on the output to minimize the amount of manual user corrections needed. This tool is part of ongoing research into the further optimization of geographic region annotation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 13, 2023
Accession Number
AD1206091

Entities

People

  • Benji J Lee
  • Bradley Landreneau
  • Christopher J. Michael
  • Nicholas M. Studer
  • Steven M. Dennis

Organizations

  • United States Naval Research Laboratory

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Classification
  • Data Science
  • Elevation
  • Errors
  • Geographic Information Systems
  • Geographic Regions
  • Geological Surveys
  • Information Systems
  • Instructions
  • Learning
  • Machine Learning
  • Oceanography
  • Quality Control
  • Remote Sensing
  • Sea Level Rise
  • Standards
  • Storm Surges
  • Surveys
  • Training
  • User Interface

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Coastal and Marine Engineering/Sediment Transport/Hydraulic Engineering
  • Computer Vision.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks